© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87941
    Prev
    Next
    INDEX
    Explanations

    structured elements related to programming and code implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĩенÑĮ
    -0.06
    .&
    -0.06
     gratuites
    -0.06
    -backend
    -0.06
    otre
    -0.06
     surround
    -0.06
    озем
    -0.06
    nit
    -0.06
    çݲ
    -0.06
    ults
    -0.06
    POSITIVE LOGITS
    amba
    0.07
    538
    0.07
    zych
    0.06
    .xmlbeans
    0.06
    conto
    0.06
    ting
    0.06
     Atlas
    0.06
     sayıda
    0.06
    ingleton
    0.06
    arget
    0.06
    Activations Density 0.006%

    No Known Activations